© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73340
    Prev
    Next
    INDEX
    Explanations

    you + hope + positive verbs

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags direct reader‐address phrases—especially “hope you …” style constructions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     However
    -1.37
     without
    -1.33
     There
    -1.27
     Several
    -1.25
     but
    -1.25
     Unfortunately
    -1.22
     ensuring
    -1.21
     only
    -1.20
     required
    -1.20
     low
    -1.17
    POSITIVE LOGITS
     komfor
    1.34
    ‘’
    1.16
    JOY
    1.16
     winkel
    1.13
     enjoy
    1.13
     ooo
    1.10
    ఝ
    1.10
     VERT
    1.10
    […]
    1.09
    runApp
    1.09
    Activations Density 0.024%

    No Known Activations