© 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. 35221
    Prev
    Next
    INDEX
    Explanations

    common preceding words

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

    most, many, majority

    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
     '_'
    0.47
    ⁻
    0.46
    ।
    0.44
     STRA
    0.43
    HEAD
    0.42
     Integrate
    0.42
     Follow
    0.41
     HEAD
    0.40
    益
    0.40
    ALSE
    0.40
    POSITIVE LOGITS
     බොහෝ
    0.46
     bukanlah
    0.46
     kebanyakan
    0.44
    並不
    0.43
    かなり
    0.43
     대부분
    0.43
    nir
    0.43
     बहुतेक
    0.43
    തല്ല
    0.43
     hohen
    0.42
    Activations Density 0.000%

    No Known Activations