© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58776
    Prev
    Next
    INDEX
    Explanations

    "Really" followed by adjectives/descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    These
    -1.64
    ࿚
    -1.58
     ".
    -1.51
     seleccione
    -1.50
    इटम
    -1.49
     selalu
    -1.48
    ଢ
    -1.46
     puedes
    -1.44
     you
    -1.42
     SHOULD
    -1.42
    POSITIVE LOGITS
     doubtnut
    1.46
     developments
    1.45
    んですけど
    1.30
     tanga
    1.25
    んですか
    1.24
     particular
    1.24
     oscuro
    1.22
    のかも
    1.22
     the
    1.20
    イケ
    1.20
    Activations Density 0.006%

    No Known Activations