© 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. 149622
    Prev
    Next
    INDEX
    Explanations

    specializing ailments check references

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

    sending commands and actions

    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
     nuance
    0.55
    튜디오
    0.47
    꿈
    0.44
     pokuš
    0.44
    劇情
    0.44
    효
    0.44
     Illusion
    0.43
     aprovechar
    0.43
    Coverage
    0.42
    እ
    0.42
    POSITIVE LOGITS
    aneously
    0.53
    ated
    0.52
    angs
    0.48
    ers
    0.48
    ometrical
    0.48
    ays
    0.47
    ioid
    0.47
    ongs
    0.46
    ia
    0.46
    aneous
    0.46
    Activations Density 0.001%

    No Known Activations