© 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. 114594
    Prev
    Next
    INDEX
    Explanations

    deriving from or of

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

    derived from or deduced from

    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
    <0x8C>
    0.66
    0.66
    em
    0.62
    ID
    0.61
    ur
    0.61
    IF
    0.59
    é
    0.58
    }}
    0.58
    isn
    0.56
     can
    0.53
    POSITIVE LOGITS
     derive
    1.21
     derived
    1.11
    derive
    1.01
     Derived
    0.98
     derivada
    0.95
     derives
    0.94
     deriva
    0.94
     deriv
    0.93
     deriving
    0.93
     derivable
    0.93
    Activations Density 0.060%

    No Known Activations