© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138637
    Prev
    Next
    INDEX
    Explanations

    asset valuation and status

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

    state a concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brev
    0.45
     amores
    0.44
     grains
    0.43
     Pest
    0.42
    Transcription
    0.42
     pearls
    0.42
     emulsions
    0.42
    浆
    0.42
     Substances
    0.41
     pouches
    0.41
    POSITIVE LOGITS
    prefab
    0.51
    when
    0.48
    buddy
    0.46
     predefined
    0.45
    university
    0.45
    applicable
    0.45
    rank
    0.44
     समान
    0.44
    tru
    0.44
    sess
    0.43
    Activations Density 0.004%

    No Known Activations