© 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. 182616
    Prev
    Next
    INDEX
    Explanations

    anywhere, everything, track, brilliant, up, whom, a, best, half

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

    immediate actions or consequences

    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
     ይህ
    0.49
    rowadz
    0.43
    画布
    0.42
    ksz
    0.42
     సరి
    0.42
     వి
    0.40
    vamente
    0.40
     音
    0.40
    带宽
    0.40
    ayt
    0.40
    POSITIVE LOGITS
    上げ
    0.50
     grundsätzlich
    0.47
    あえず
    0.47
     Gera
    0.47
    ⊆
    0.46
    とりあえず
    0.46
    上前
    0.45
     일단
    0.45
     देवता
    0.45
    昔
    0.45
    Activations Density 0.001%

    No Known Activations